Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Fix] handle prompt length for multi-GPU #87

Merged
merged 10 commits into from
Dec 9, 2024
Merged

[Fix] handle prompt length for multi-GPU #87

Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
4205fd0
Merge pull request #63 from sbintuitions/dev
lsz05 Aug 30, 2024
fd5d438
Merge pull request #68 from sbintuitions/dev
lsz05 Aug 30, 2024
1d17444
Merge pull request #82 from sbintuitions/dev
akiFQC Nov 21, 2024
ee34da4
turn prompt_length from int into tensor
hppRC Dec 6, 2024
e4149e9
fix: made DPSbertEmbedder work with prompts.
hppRC Dec 9, 2024
97f5502
Merge https://github.com/sbintuitions/JMTEB into fix/handle_prompt_le…
hppRC Dec 9, 2024
672e8ba
fix: refactor
hppRC Dec 9, 2024
6428c19
fix: argument name
hppRC Dec 9, 2024
f177e60
:+1: changed the import source of `models` and added comments.
hppRC Dec 9, 2024
1d3d846
:+1: supress a lint error
hppRC Dec 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
👍 changed the import source of models and added comments.
  • Loading branch information
@hppRC
hppRC committed Dec 9, 2024
commit f177e60436fc7edb8739086a3102d837462d7d7b
7 changes: 5 additions & 2 deletions src/jmteb/embedders/data_parallel_sbert_embedder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,8 @@
import torch
from accelerate.utils import find_executable_batch_size
from loguru import logger
from sentence_transformers import SentenceTransformer, models
from sentence_transformers import SentenceTransformer
from sentence_transformers.models import Pooling
from sentence_transformers.quantization import quantize_embeddings
from sentence_transformers.util import truncate_embeddings
from torch import Tensor
Expand Down Expand Up @@ -166,9 +167,11 @@ def encode(

return all_embeddings

# Sentence Transformersの`include_prompt`判定メソッドを参考に実装
# ref: https://github.com/UKPLab/sentence-transformers/blob/679ab5d38e4cf9cd73d4dcf1cda25ba2ef1ad837/sentence_transformers/trainer.py#L931
def include_prompt_for_pooling(self) -> bool:
for module in self:
if isinstance(module, models.Pooling):
if isinstance(module, Pooling):
return module.include_prompt
return True

Expand Down
Loading